Given the large volume of technical documents available, it is crucial to automatically organize and categorize these documents to be able to understand and extract value from them. Towards this end, we introduce a new research problem called Facet Extraction. Given a collection of technical documents, the goal of Facet Extraction is to automatically label each document with a set of concepts for the key facets (e.g., application, technique, evaluation metrics, and dataset) that people may be interested in. Facet Extraction has numerous applications, including document summarization, literature search, patent search and business intelligence. The major challenge in performing Facet Extraction arises from multiple sources: concept extraction, concept to facet matching, and facet disambiguation. To tackle these challenges, we develop FacetGist, a framework for facet extraction. Facet Extraction involves constructing a graph-based heterogeneous network to capture information available across multiple local sentence-level features, as well as global context features. We then formulate a joint optimization problem, and propose an efficient algorithm for graph-based label propagation to estimate the facet of each concept mention. Experimental results on technical corpora from two domains demonstrate that Facet Extraction can lead to an improvement of over 25% in both precision and recall over competing schemes.

There is wide agreement that the mind has different mechanisms it can use to make moral judgments. But how does it decide which one to use when? Recent theoretical work has suggested that people select mechanisms of moral judgment in a way that is resource-rational --- that is, by rationally trading off effort against utility. For instance, people may follow general rules in low-stakes situations, but engage more computationally intensive mechanisms such as consequentialist or contractualist reasoning when the stakes are high. Here, we evaluate whether humans and large language models (LLMs) exhibit resource-rational moral reasoning in two moral dilemmas by manipulating the stakes of each scenario. As predicted, we found that the higher the stakes, the more people employed a more effortful mechanism over following a general rule. However, there was mixed evidence for similar resource-rational moral reasoning in the LLMs. Our results provide evidence that people's moral judgments reflect resource-rational cognitive constraints, and they highlight the opportunities for developing AI systems better aligned with human moral values.

Pericyclic reactions are powerful transformations for the construction of carbon-carbon and carbon-heteroatom bonds in organic synthesis. Their role in biosynthesis is increasingly apparent, and mechanisms by which pericyclases can catalyse reactions are of major interest¹. [4+2] cycloadditions (Diels-Alder reactions) have been widely used in organic synthesis² for the formation of six-membered rings and are now well-established in biosynthesis^3-6. [6+4] and other 'higher-order' cycloadditions were predicted⁷ in 1965, and are now increasingly common in the laboratory despite challenges arising from the generation of a highly strained ten-membered ring system^8,9. However, although enzyme-catalysed [6+4] cycloadditions have been proposed^10-12, they have not been proven to occur. Here we demonstrate a group of enzymes that catalyse a pericyclic [6+4] cycloaddition, which is a crucial step in the biosynthesis of streptoseomycin-type natural products. This type of pericyclase catalyses [6+4] and [4+2] cycloadditions through a single ambimodal transition state, which is consistent with previous proposals^11,12. The [6+4] product is transformed to a less stable [4+2] adduct via a facile Cope rearrangement, and the [4+2] adduct is converted into the natural product enzymatically. Crystal structures of three pericyclases, computational simulations of potential energies and molecular dynamics, and site-directed mutagenesis establish the mechanism of this transformation. This work shows how enzymes are able to catalyse concerted pericyclic reactions involving ambimodal transition states.